Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Core
    -0.08
    ivities
    -0.08
    ktf
    -0.07
    .documentation
    -0.07
    Pointer
    -0.07
    বান
    -0.07
     লাভ
    -0.07
     ganho
    -0.07
    .Documents
    -0.07
     könnten
    -0.07
    POSITIVE LOGITS
    cat
    0.08
     cats
    0.08
    (cat
    0.08
     �
    0.08
    _cat
    0.08
     Jackie
    0.07
     해서
    0.07
    ейки
    0.07
     cat
    0.07
    자인
    0.07
    Act Density 0.068%

    No Known Activations